Related papers: DiTFastAttnV2: Head-wise Attention Compression for…

Text-to-image (T2I) diffusion models lack an efficient mechanism for early quality assessment, leading to costly trial-and-error in multi-generation scenarios such as prompt iteration, agent-based generation, and flow-grpo. We reveal a…

Recent diffusion models enable high-quality video generation, but suffer from slow runtimes. The large transformer-based backbones used in these models are bottlenecked by spatiotemporal attention. In this paper, we identify that a…

Achieving ID-preserving text-to-video (T2V) generation remains challenging despite recent advances in diffusion-based models. Existing approaches often fail to capture fine-grained facial dynamics or maintain temporal identity coherence. To…

Diffusion Transformers (DiTs) achieve state-of-the-art video generation quality, but their substantial memory and computational footprints hinder edge deployment. Quantization can reduce these costs, yet existing methods often degrade video…

We propose DiTFlow, a method for transferring the motion of a reference video to a newly synthesized one, designed specifically for Diffusion Transformers (DiT). We first process the reference video with a pre-trained DiT to analyze…

Diffusion Transformers (DiT) have become the dominant methods in image and video generation yet still suffer substantial computational costs. As an effective approach for DiT acceleration, feature caching methods are designed to cache the…

In this work, we introduce HeFT (Head-Frequency Tracker), a zero-shot point tracking framework that leverages the visual priors of pretrained video diffusion models. To better understand how they encode spatiotemporal information, we…

Image fusion aims to blend complementary information from multiple sensing modalities, yet existing approaches remain limited in robustness, adaptability, and controllability. Most current fusion networks are tailored to specific tasks and…

Existing text-to-image diffusion models struggle to synthesize realistic images given dense captions, where each text prompt provides a detailed description for a specific image region. To address this, we propose DenseDiffusion, a…

The most advanced text-to-image (T2I) models require significant training costs (e.g., millions of GPU hours), seriously hindering the fundamental innovation for the AIGC community while increasing CO2 emissions. This paper introduces…

Designing model architectures requires decisions such as selecting operators (e.g., attention, convolution) and configurations (e.g., depth, width). However, evaluating the impact of these decisions on model quality requires costly…

Autoregressive (AR) video diffusion models adopt a streaming generation framework, enabling long-horizon video generation with real-time responsiveness, as exemplified by the Self Forcing training paradigm. However, existing AR video…

Diffusion models excel in high-fidelity image generation but face scalability limits due to transformers' quadratic attention complexity. Plug-and-play token reduction methods like ToMeSD and ToFu reduce FLOPs by merging redundant tokens in…

Diffusion Transformer (DiT), an emerging diffusion model for visual generation, has demonstrated superior performance but suffers from substantial computational costs. Our investigations reveal that these costs primarily stem from the…

The computational demands of self-attention mechanisms pose a critical challenge for transformer-based video generation, particularly in synthesizing ultra-long sequences. Current approaches, such as factorized attention and fixed sparse…

Despite recent significant strides achieved by diffusion-based Text-to-Image (T2I) models, current systems are still less capable of ensuring decent compositional generation aligned with text prompts, particularly for the multi-object…

Recent advances have demonstrated the powerful capability of transformer architecture in image restoration. However, our analysis indicates that existing transformerbased methods can not establish both exact global and local dependencies…

Despite their generative power, diffusion models struggle to maintain style consistency across images conditioned on the same style prompt, hindering their practical deployment in creative workflows. While several training-free methods…

Training-free control over editing intensity is a critical requirement for diffusion-based image editing models built on the Diffusion Transformer (DiT) architecture. Existing attention manipulation methods focus exclusively on the Key…

The quadratic complexity of the attention mechanism severely limits the context scalability of Video Diffusion Transformers (DiTs). We find that the highly sparse spatio-temporal attention patterns exhibited in Video DiTs can be naturally…